Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The annotations already flag destructiveHint=true, but the description adds the crucial behavioral detail those hints cannot: existing language criteria are overwritten, not merged, and an empty array silently means 'target all languages'. That is exactly the kind of consequence an agent needs before invoking a destructive call.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

Three short clauses, each load-bearing: the replace semantics first, the example second, the empty-list gotcha third, then the optional workspace note. No filler and the most consequential information is front-loaded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 3-parameter destructive mutation with an output schema present and safety hints already in annotations, this covers what an agent must know to call it correctly: overwrite behavior, empty-list meaning, and workspace scoping. Nothing material is missing.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 0%, so the description carries the load: it documents language_codes format with a concrete example (["de", "en"]) and its empty-list edge case, plus the optional workspace slug clause for single-workspace accounts. It leaves campaign_id and the exact accepted code format (ISO code vs. Google Ads language constant) unstated, so it compensates well but not fully.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

Specific verb and resource: "Sprach-Targeting einer Kampagne SETZEN" with the parenthetical "(ersetzt die Auswahl)" that makes it a replace operation rather than an additive one. This distinguishes it from the read-side sibling ads_get_language_targeting and from the additive ads_add_audience_signal-style tools without opening any schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

Clear operational context is given: a non-empty list replaces the selection and an empty list clears all language criteria (= all languages). However, no sibling alternative is named and no precondition (e.g. campaign must be paused / must exist) is stated, so it stops short of explicit when/when-not routing.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.